A Genetic Algorithm-Driven Energy-Efficient Routing Strategy for Optimizing Performance in VANETs

VANETs are now essential for smart transportation because they make it possible for vehicles and road infrastructure to send and receive messages instantly. However, WSN routes are challenged by the movement and the limited energy of the nodes, along with the number of vehicles. This study presents a new GA-based routing technique to control packet delivery and reduce total energy consumption in VANETs. A VANET with 500 vehicles was modeled in a 1000×1000 m² area, using 1 J of energy per vehicle and limiting communication to within 150 m of each vehicle. Each candidate route is examined using a fitness function that is lower when the energy cost is higher. Using tournament selection, natural crossover, and energy-aware mutation, the GA supports the adaptation of efficient, loop-free paths linking the source and the sink in multi-hop networks. The simulation results confirm that the proposed scheme is better than AODV and DSR, delivering 92.5% of packets and achieving a reduced delay of 45.2 ms. This strategy reduces energy consumption, so the network can function longer, demonstrating how the proposed method fits changing conditions in VANET networks. The framework can be adapted for ITS and can be integrated with learning-based predictions for mobility and federated routing.